© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 14576
    Prev
    Next
    INDEX
    Explanations

    phrases related to negative aspects or criticisms, particularly in a social or governmental context

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.12
    0.4%
    855
    +0.10
    0.3%
    204
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.12
    0.02
    378
    +0.10
    0.03
    855
    +0.09
    0.03
    Negative Logits
    conditionally
    -0.58
     &&
    -0.48
    ->___
    -0.48
     uwag
    -0.46
    sumowanie
    -0.46
    umacher
    -0.45
     objectMapper
    -0.45
    ForRow
    -0.45
     –
    -0.45
    olphe
    -0.45
    POSITIVE LOGITS
     fte
    0.96
     ordina
    0.94
     fta
    0.92
     „,
    0.91
     wien
    0.91
     dises
    0.88
     ftu
    0.88
     umbro
    0.88
     funghi
    0.87
     milano
    0.87
    Activations Density 0.112%

    No Known Activations